Need help with syncnet_python?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

226 Stars 82 Forks MIT License 24 Commits 18 Opened issues


Out of time: automated lip sync in the wild

Services available


Need anything else?

Contributors list

No Data


This repository contains the demo for the audio-to-video synchronisation network (SyncNet). This network can be used for audio-visual synchronisation tasks including: 1. Removing temporal lags between the audio and visual streams in a video; 2. Determining who is speaking amongst multiple faces in a video.

Please cite the paper below if you make use of the software.


pip install -r requirements.txt

In addition,

is required.


SyncNet demo:

python --videofile data/example.avi --tmp_dir /path/to/temp/directory

Check that this script returns:

AV offset:      3 
Min dist:       5.353
Confidence:     10.021

Full pipeline:

python --videofile /path/to/video.mp4 --reference name_of_video --data_dir /path/to/output
python --videofile /path/to/video.mp4 --reference name_of_video --data_dir /path/to/output
python --videofile /path/to/video.mp4 --reference name_of_video --data_dir /path/to/output


$DATA_DIR/pycrop/$REFERENCE/*.avi - cropped face tracks
$DATA_DIR/pywork/$REFERENCE/offsets.txt - audio-video offset values
$DATA_DIR/pyavi/$REFERENCE/video_out.avi - output video (as shown below)


  author       = "Chung, J.~S. and Zisserman, A.",
  title        = "Out of time: automated lip sync in the wild",
  booktitle    = "Workshop on Multi-view Lip-reading, ACCV",
  year         = "2016",

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.